group text

meetus/transcript_merger.py

@@ -17,7 +17,7 @@ class TranscriptMerger:
         """Initialize transcript merger."""
         pass
 
-    def load_whisper_transcript(self, transcript_path: str) -> List[Dict]:
+    def load_whisper_transcript(self, transcript_path: str, group_interval: Optional[int] = None) -> List[Dict]:
         """
         Load Whisper transcript from file.
 
@@ -25,6 +25,7 @@ class TranscriptMerger:
 
         Args:
             transcript_path: Path to transcript file
+            group_interval: If specified, group audio segments into intervals (in seconds)
 
         Returns:
             List of dicts with 'timestamp' (optional) and 'text'
@@ -36,9 +37,10 @@ class TranscriptMerger:
                 data = json.load(f)
 
             # Handle different Whisper output formats
+            segments = []
             if isinstance(data, dict) and 'segments' in data:
                 # Standard Whisper JSON format
-                return [
+                segments = [
                     {
                         'timestamp': seg.get('start', 0),
                         'text': seg['text'].strip(),
@@ -48,7 +50,7 @@ class TranscriptMerger:
                 ]
             elif isinstance(data, list):
                 # List of segments
-                return [
+                segments = [
                     {
                         'timestamp': seg.get('start', seg.get('timestamp', 0)),
                         'text': seg['text'].strip(),
@@ -57,6 +59,12 @@ class TranscriptMerger:
                     for seg in data
                 ]
 
+            # Group by interval if requested
+            if group_interval and segments:
+                segments = self.group_audio_by_intervals(segments, group_interval)
+
+            return segments
+
         else:
             # Plain text file - no timestamps
             with open(path, 'r', encoding='utf-8') as f:
@@ -68,6 +76,50 @@ class TranscriptMerger:
                 'type': 'audio'
             }]
 
+    def group_audio_by_intervals(self, segments: List[Dict], interval_seconds: int = 30) -> List[Dict]:
+        """
+        Group audio segments into regular time intervals.
+
+        Instead of word-level timestamps, this creates intervals (e.g., every 30 seconds)
+        with all text spoken during that interval concatenated together.
+
+        Args:
+            segments: List of audio segments with timestamps
+            interval_seconds: Duration of each interval in seconds
+
+        Returns:
+            List of grouped segments with interval timestamps
+        """
+        if not segments:
+            return []
+
+        # Find the max timestamp to determine how many intervals we need
+        max_timestamp = max(seg['timestamp'] for seg in segments)
+        num_intervals = int(max_timestamp / interval_seconds) + 1
+
+        # Create interval buckets
+        intervals = []
+        for i in range(num_intervals):
+            interval_start = i * interval_seconds
+            interval_end = (i + 1) * interval_seconds
+
+            # Collect all text in this interval
+            texts = []
+            for seg in segments:
+                if interval_start <= seg['timestamp'] < interval_end:
+                    texts.append(seg['text'])
+
+            # Only create interval if there's text
+            if texts:
+                intervals.append({
+                    'timestamp': interval_start,
+                    'text': ' '.join(texts),
+                    'type': 'audio'
+                })
+
+        logger.info(f"Grouped {len(segments)} segments into {len(intervals)} intervals of {interval_seconds}s")
+        return intervals
+
     def merge_transcripts(
         self,
         audio_segments: List[Dict],